Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    terms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    enums
    -0.08
    wig
    -0.08
     comerc
    -0.08
    /public
    -0.07
    umes
    -0.07
    (off
    -0.07
    [:
    -0.07
    除非
    -0.07
    .UseText
    -0.07
    翥
    -0.07
    POSITIVE LOGITS
    的做法
    0.07
     Vehicle
    0.07
     Fav
    0.07
     שונים
    0.07
    back
    0.07
     아닌
    0.07
    宝贝
    0.07
     своими
    0.07
    Bracket
    0.07
    Rights
    0.07
    Act Density 0.038%

    No Known Activations